Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
RL Tutorial
In this presentation, I introduce RL algorithms from dynamic programming (value iteration, policy iteration) to Q-learning (Monte-Carlo and Temporal-Difference prediction, deep Q-network) to policy gradient (REINFORCE, proximal policy gradient, and soft actor-critic). Additionally, I discuss some of the recent advances in safe and multiagent RL and some other directions.
General Examination Abstract
Recent developments in deep reinforcement learning have shown promising results to improve the capabilities of autonomous systems. However, for safety-critical robotic systems, it is crucial to provide safety and liveness certificates around these data-driven methods.
past_projects
Energy-Efficient Real-Time Electrocardiography Telemonitoring
Published in IEEE GlobalSIP, 2018
Joint Estimation of DOA and Carrier Frequency
Published in Sensors, 2019
On-demand Reconstruction for Compressively Sensed Problematic Signals
Published in IEEE Trans. Signal Process., 2020
portfolio
research
Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning
Published in RSS, 2021
Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees
Published in Artificial Intelligence, 2022
ISAACS: Iterative Soft Adversarial Actor Critic for Safety
Published in L4DC, 2023
Interpretable Trajectory Prediction for Autonomous Vehicles via Counterfactual Responsibility
Published in IROS, 2023
